© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13046
    Prev
    Next
    INDEX
    Explanations

    thread/conversation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thread
    -1.03
    thread
    -0.93
     THREAD
    -0.90
     threads
    -0.88
    Thread
    -0.84
     Thread
    -0.84
    THREAD
    -0.83
    threaded
    -0.76
    Threads
    -0.74
     threaded
    -0.73
    POSITIVE LOGITS
     SwitchCompat
    0.63
    fromnode
    0.57
     consultato
    0.57
    bardier
    0.57
    GeneratedValue
    0.56
     typelib
    0.55
     dAtA
    0.54
    BASELINE
    0.53
    ixante
    0.53
    setVerticalGroup
    0.52
    Activations Density 0.012%

    No Known Activations